Combined artificial bee colony algorithm and machine learning techniques for prediction of online consumer repurchase intention

Transactions through the web are now a progressive mechanism to access an ever-increasing range of services over more and more diverse environments. The internet provides many opportunities for companies to provide personalized online services to their customers, but the quality and novelty of some web services may adversely affect the appeal and user gratification. In the future, prediction of the consumer intention needs to be a main focus for selecting the web services for an application. The aim of this study is to predict online consumer repurchase intentions; to accomplish this objective a hybrid approach is chosen with a combination of machine learning techniques and artificial bee colony (ABC) algorithm being used. The study starts with identification of consumer characteristics for repurchase intention, followed by determining the feature selection of consumer characteristics and shopping mall attributes (with >0.1 threshold value) for the prediction model using ABC. Finally, validation using k-fold cross has been employed to measure the best classification model robustness. The classification models, viz. decision trees (C5.0), AdaBoost, random forest, support vector machine and neural network, are utilized to predict consumer purchase intention. Performance evaluation of identified models on training–testing partitions (70–30%) of the data set shows that the AdaBoost method outperforms other classification models, with sensitivity and accuracy of 0.95 and 97.58%, respectively, on testing the data set. Examining the consumer repurchase intentions by considering both shopping mall and consumer characteristics makes this study unique.

     

Bi-objective approach for computer-aided diagnosis of schizophrenia patients using fMRI data

Multimedia Tools and Applications - Computer-aided diagnosis (CAD) of schizophrenia based on the analysis of brain images, captured using functional Magnetic Resonance Imaging (fMRI) technique, is...     

Weakly Supervised and Online Learning of Word Models for Classification to Detect Disaster Reporting Tweets

Social media has quickly established itself as an important means that people, NGOs and governments use to spread information during natural or man-made disasters, mass emergencies and crisis situations. Given this important role, real-time analysis of social media contents to locate, organize and use valuable information for disaster management is crucial. In this paper, we propose self-learning algorithms that, with minimal supervision, construct a simple bag-of-words model of information expressed in the news about various natural disasters. Such a model is human-understandable, human-modifiable and usable in a real-time scenario. Since tweets are a different category of documents than news, we next propose a model transfer algorithm, which essentially refines the model learned from news by analyzing a large unlabeled corpus of tweets. We show empirically that model transfer improves the predictive accuracy of the model. We demonstrate empirically that our model learning algorithm is better than several state of the art semi-supervised learning algorithms. Finally, we present an online algorithm that learns the weights for words in the model and demonstrate the efficacy of the model with word weights.     

Imidazolium‐Based Ionic Liquid as Modulator of Physicochemical Properties of Cationic,Anionic, Nonionic,and Gemini Surfactants

The aggregation morphology of 2 cationic surfactants (cetyldimethylethanolammonium bromide and cetyldiethylethanolammonium bromide), an anionic surfactant (sodium dodecylbenzenesulfonate), a nonionic surfactant (Triton X‐100), and 2 gemini surfactants (16‐4‐16,2Br^?[butanediyi‐1,4‐bis(dimethyldohexylammonium bromide)] and 16‐6‐16,2Br^?[hexanediyi‐1,6‐bis(dimethyldohexylammonium bromide)]) in the presence of the ionic liquid (IL) 1‐ethyl‐3‐methylimidazoliumbromide [Emim][Br] is studied using various techniques such as surface tension, conductivity, and UV–visible and fluorescence spectroscopy. Increasing the concentration of [Emim][Br] results in a decrease in the critical micelle concentration (CMC) value of the surfactants. Various interfacial properties, namely the surface excess concentration (Г_max), minimum area per molecule at the air–water interface (A_min)_, and surface pressure at the CMC (π_cmc), as well as the thermodynamic parameters such as free energy of the given air/water interface (), Gibbs free energy of micelle formation (), Gibbs free energy of micellization per alkyl tail (), Gibbs energy of transfer (), and standard free energy of adsorption () were also investigated. The aggregation number (N_agg) was determined by the fluorescence method. It was observed that N_agg decreased with increasing weight‐percent of the IL.     

Dielectric relaxations in phosphoric acid‐doped poly(2,5‐benzimidazole) and its composite membranes

Poly(2,5‐benzimidazole) (ABPBI)—a promising high‐temperature polymer electrolyte membrane—is characterized over a wide range of temperature (?50 to 220 °C) using broadband dielectric spectroscopy (BDS) to understand the various relaxation processes. The undoped ABPBI membrane shows two major secondary relaxations and a primary α relaxation. The effect of phosphoric acid (PA) and phosphotungstic acid grafted zirconium dioxide (PWA/ZrO₂) nanoparticles on the chain relaxation and the proton conductivity is investigated. The phosphoric acid alters the relaxation trends, increases the number of free ions in the polymer matrix, and therefore the conductivity. The shift in the peak frequencies of different chain relaxation processes in the presence of PA and PWA/ZrO₂ is attributed to the increase in free volume and the consequent easy motion of the polymer chains. The Fourier transform infra‐red (FTIR) spectroscopy of ABPBI and the acid‐doped composites show all the relevant peaks corresponding to C?C, C?N stretching, and phosphoric acid/phosphates, confirming the formation of ABPBI and doping with PA. The proton conductivity of the membranes is estimated from electrochemical impedance spectroscopy (EIS). To establish the effect of change in crystallinity on relaxations and proton conductivity, the undoped and PA‐doped membranes are characterized using thermogravimetric analysis and in situ XRD at high temperatures. © 2017 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2017 , 134 , 44867.     

Tribological and thermal properties of hexagonal boron nitride filled high‐performance polymer nanocomposites

High‐performance polymer nanocomposites based on poly(aryletherketone) (PAEK) as matrix and hexagonal boron nitride (h‐BN) nanopowder as reinforcement were fabricated using planetary ball mill followed by hot pressing. The addition of h‐BN (0–5 wt %) to the matrix enhanced the microhardness and thermal stability compared to pure matrix. For a constant sliding speed, the wear rate of the nanocomposites determined by using Pin‐on‐Disk tribometer was reduced approximately 22 times compared to pure matrix. The coefficient of friction of the nanocomposites is slightly increased but it is stable compared to that of pure matrix. It was also investigated that the thermal stability of the debris of the nanocomposites was decreased compared to the pure matrix and its nanocomposites. © 2016 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2017 , 134, 44409.     

存储域网络中的线卡解决方案

近几年来,Internet的平均带宽每6～9个月向上翻一倍,因而网络传输能力(带宽)和存储能力(存储Internet上来来往往的数据)都面临严峻挑战。电子商务、数据挖掘、数据库、客户关系管理等网络应用产生并要求处理大量的数据,同时还提出容错要求和全局24/7的数据存取速度要求。所有这些都迫切要求大容量的、快速高效的存储方案。传统的多服务器分布式存储系统已不能满足要求。     

Synthesis of New Metastable Aluminum-Titanium Alloy by Defying Equilibrium in an Equilibrium Process

In this article, the synthesis of a newer generation of metastable aluminum- titanium (Al-Ti) materials is presented and discussed. Two equilibrium processing methods, using disintegrated melt deposition, were chosen and tried. The first restricted the interaction time between powders of titanium and molten aluminum, whereas the second essentially involved a change in surface characteristics of titanium powders prior to their addition to molten aluminum. The results of microstructural characterization and X-ray diffraction studies conducted on the Al-Ti materials, synthesized using the two methods, reveal the presence of elemental titanium and other phases in the aluminum matrix, thereby providing confirmation as to the metastable nature of these materials. Results also indicate that a significantly higher amount of titanium can be retained in the metal matrix at low processing temperatures when compared with predictions of the equilibrium Al-Ti phase diagram. Results of this study provide an innovative, viable, and cost-effective approach to synthesize metastable materials for both scientific and engineering applications.     

Encapsulation of air‐filled poly(dimethylsiloxane) microballoons in polyimide as a polymeric low ε dielectric

Air‐filled microballoons of poly(dimethylsiloxane), ie PDMS, have been encapsulated in polyimide. The molecular assembly so formed has shown surface dominance by PDMS while analytical techniques, such as X‐ray photoelectron spectroscopy and infrared spectroscopy, have confirmed a similar distribution in the bulk. The electrical properties of the resultant polymer have been studied and the relative permittivity has been found to be very low while other beneficial attributes of the polyimide have been retained. Copyright © 2004 Society of Chemical Industry